Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Deutsches, kein, keine, Kindern, Sprachen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    घा
    0.45
    φαι
    0.45
    ናል
    0.43
    stvu
    0.42
    比如说
    0.42
    ぶ
    0.42
    ibles
    0.41
    ghis
    0.41
    cq
    0.41
    REP
    0.41
    POSITIVE LOGITS
     Deutsches
    0.60
     kein
    0.57
     keine
    0.56
     Alta
    0.55
     Weitere
    0.54
     Keine
    0.50
     Kindern
    0.50
     Sprachen
    0.50
     Beaver
    0.49
     H
    0.48
    Act Density 0.031%

    No Known Activations